Tag

#Commerce

188 results found

Shippo
@Shippo

a month ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

2 months ago
MarketNow — Trust Layer for Agent Commerce (MCP Marketplace)
@Edison Flores

The trust layer for agent commerce. 8,560 MCP-compatible skills with Sentinel L2 security audits, x402 payments (HTTP 402 + USDC on Base), and AP2 delegated mandates with human-in-the-loop by default. NOT another discovery registry — discovery is solved (MCP Registry, Smithery, Glama). MarketNow solves TRUST: every skill carries a Sentinel security report, declared permissions, and an honest review_status (auto-scanned | human-reviewed | maintainer-verified). ## What's different - 🔒 Sentinel L2: real-time security audit on every skill (18 Semgrep rules + Docker sandbox + OSV dependency check) - 💳 x402 + USDC on Base: HTTP 402 Payment Required, on-chain verifiable - 🛡️ AP2 mandates: agents buy autonomously, but human-in-the-loop is the DEFAULT (not opt-out) - 📜 Audit log = git commits: every mandate transaction is a public commit in the GitHub repo - 🌍 5 languages: EN, ES, ZH, PT, FR - 💰 $0.99–$9.99 one-time, 43 free skills, NO subscriptions - 🏢 Built by AliceLabs LLC (Wyoming, USA, 2025), solo founder Edison Flores, no investors ## MCP Tools - search_skills: Search by query, category, price, language - get_skill: Get full details (system prompt, sentinel, setup) - list_categories: 58 categories with counts - get_manifest: Marketplace metadata - get_install_command: Get npx install command ## Server Config { "mcpServers": { "marketnow": { "url": "https://marketnow.site/api/mcp" } } } ## Stats (live) - 8,560 MCP skills indexed - 58 categories - 43 free skills - 5 languages - License: MNNC-1.0 (source-available, non-commercial) ## Links - Website: https://marketnow.site - Trust roadmap: https://marketnow.site/trust - Standards: https://marketnow.site/standards - Source: https://github.com/edgarfloresguerra2011-a11y/marketnow - npm: https://www.npmjs.com/package/marketnow-mcp - OpenAPI: https://marketnow.site/api/openapi.json Built for autonomous agents. Every skill has a Sentinel security report, a ready-to-use system prompt, and auto-configured install. What you pay for is trust, curation, and integration — not the code (which is open source).

17 days ago